Research map / Reinforcement learning / Visual and representation RL
Adaptive optimal training of animal behavior
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Select stimuli with AlignMax instead of presenting stimuli randomly | Simulated noise-free RewardMax learner · Full stimulus space | training speed (success rate, expected reward, KL divergence) | Helped |
| Train on the full stimulus plane instead of the reduced set of stimuli near the boundary (ablation) | AlignMax trainer · Simulated learner | training speed | Helped |
| Use AlignMax instead of random training for removing bias b and history dependence h | Simulated learner · Figure 4A weights | time to eliminate bias and history dependence | Helped |
| Use AlignMax instead of random training | Simulated learner · Success rate during training | success rate | Hurt |
| Increase number of history terms d in the psychometric model (ablation) | Rat GLM · Rat dataset early/mid/late | BIC: best d = 1 near end of dataset | Mixed |
| Incorporate RewardMax drift term in the random-walk prior | Weight estimation on simulated learner · Simulated learner, sigma_sim = alpha_sim = 2−7 | parameter recovery | Helped |
Closest papers by meaning
- Inferring learning rules from animal decision-making (NeurIPS 2020 · similarity 0.93)
- Efficient inference for time-varying behavior during learning (NeurIPS 2018 · similarity 0.91)
- Flexible inference for animal learning rules using neural networks (NeurIPS 2025 · similarity 0.89)
- Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors (ICML 2025 · similarity 0.87)
- Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning (ICML 2024 · similarity 0.86)
- Behavioral Exploration: Learning to Explore via In-Context Adaptation (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.